Making sense of numerical data - semantic labelling of web tables

Magdalena Kacprzak Emilia; Jose M. Gimenez-Garcia; Alessandro Piscopo; Mylena Koesten Laura; Luis Ibanez Gonzalez; Jeni Tennison; Elena Simperl

Making sense of numerical data - semantic labelling of web tables

Magdalena Kacprzak Emilia
, Jose M. Gimenez-Garcia
, Alessandro Piscopo
, Mylena Koesten Laura
, Luis Ibanez Gonzalez
, Jeni Tennison
, Elena Simperl

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

15 Citations (Scopus)

Abstract

With the increasing amount of structured data on the web the need to understand and support search over this emerging data space is growing. Adding semantics to structured data can help address existing challenges in data discovery, as it facilitates understanding the values in their context. While there are approaches on how to lift structured data to semantic web formats to enrich it and facilitate discovery, most work to date focuses on textual fields rather than numerical data. In this paper, we propose a two level (row and column based) approach to add semantic meaning to numerical values in tables, called NUMER. We evaluate our approach using a benchmark (NumDB) generated for the purpose of this work. We show the influence of the different levels of analysis on the success of assigning semantic labels to numerical values in tables. Our approach outperforms the state of the art and is less affected by data structure and quality issues such as a small number of entities or deviations in the data.

Original language	Undefined/Unknown
Title of host publication	Knowledge Engineering and Knowledge Management
Publisher	SPRINGER
Publication status	Published - 1 Nov 2018

Publication series

Name	11313
Publisher	Springer

Keywords

Semantic Labelling
Numerical Values
Linked Data

Access to Document

https://eprints.soton.ac.uk/426723/

Cite this

@inbook{50a1fd6896774c4794ff3fce6a0ed9d7,

title = "Making sense of numerical data - semantic labelling of web tables",

abstract = "With the increasing amount of structured data on the web the need to understand and support search over this emerging data space is growing. Adding semantics to structured data can help address existing challenges in data discovery, as it facilitates understanding the values in their context. While there are approaches on how to lift structured data to semantic web formats to enrich it and facilitate discovery, most work to date focuses on textual fields rather than numerical data. In this paper, we propose a two level (row and column based) approach to add semantic meaning to numerical values in tables, called NUMER. We evaluate our approach using a benchmark (NumDB) generated for the purpose of this work. We show the influence of the different levels of analysis on the success of assigning semantic labels to numerical values in tables. Our approach outperforms the state of the art and is less affected by data structure and quality issues such as a small number of entities or deviations in the data.",

keywords = "Semantic Labelling, Numerical Values, Linked Data",

author = "Emilia, \{Magdalena Kacprzak\} and Gimenez-Garcia, \{Jose M.\} and Alessandro Piscopo and Laura, \{Mylena Koesten\} and Gonzalez, \{Luis Ibanez\} and Jeni Tennison and Elena Simperl",

year = "2018",

month = nov,

day = "1",

language = "Undefined/Unknown",

series = "11313",

publisher = "SPRINGER",

booktitle = "Knowledge Engineering and Knowledge Management",

}

TY - CHAP

T1 - Making sense of numerical data - semantic labelling of web tables

AU - Emilia, Magdalena Kacprzak

AU - Gimenez-Garcia, Jose M.

AU - Piscopo, Alessandro

AU - Laura, Mylena Koesten

AU - Gonzalez, Luis Ibanez

AU - Tennison, Jeni

AU - Simperl, Elena

PY - 2018/11/1

Y1 - 2018/11/1

N2 - With the increasing amount of structured data on the web the need to understand and support search over this emerging data space is growing. Adding semantics to structured data can help address existing challenges in data discovery, as it facilitates understanding the values in their context. While there are approaches on how to lift structured data to semantic web formats to enrich it and facilitate discovery, most work to date focuses on textual fields rather than numerical data. In this paper, we propose a two level (row and column based) approach to add semantic meaning to numerical values in tables, called NUMER. We evaluate our approach using a benchmark (NumDB) generated for the purpose of this work. We show the influence of the different levels of analysis on the success of assigning semantic labels to numerical values in tables. Our approach outperforms the state of the art and is less affected by data structure and quality issues such as a small number of entities or deviations in the data.

AB - With the increasing amount of structured data on the web the need to understand and support search over this emerging data space is growing. Adding semantics to structured data can help address existing challenges in data discovery, as it facilitates understanding the values in their context. While there are approaches on how to lift structured data to semantic web formats to enrich it and facilitate discovery, most work to date focuses on textual fields rather than numerical data. In this paper, we propose a two level (row and column based) approach to add semantic meaning to numerical values in tables, called NUMER. We evaluate our approach using a benchmark (NumDB) generated for the purpose of this work. We show the influence of the different levels of analysis on the success of assigning semantic labels to numerical values in tables. Our approach outperforms the state of the art and is less affected by data structure and quality issues such as a small number of entities or deviations in the data.

KW - Semantic Labelling

KW - Numerical Values

KW - Linked Data

M3 - Conference paper

T3 - 11313

BT - Knowledge Engineering and Knowledge Management

PB - SPRINGER

ER -